© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14858
    Prev
    Next
    INDEX
    Explanations

    fleeting visual phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _tables
    -0.25
    ç¿»å¼Ģ
    -0.24
    romise
    -0.22
    æµģåIJij
    -0.22
     earthqu
    -0.22
    å¥¥åľ°
    -0.21
    ãģĬãģĻãģĻ
    -0.21
     رس
    -0.21
    .oracle
    -0.21
    elper
    -0.20
    POSITIVE LOGITS
    çī©ä½ĵ
    0.24
    空ä¸Ń
    0.22
    åľ¨åľ°ä¸Ĭ
    0.22
    çĸijä¼¼
    0.21
    çݰ身
    0.21
    é«ĺ空
    0.21
     обÑĬекÑĤ
    0.21
    åįļè§Ī
    0.20
    æĸĩåĮĸèīºæľ¯
    0.20
    YouTube
    0.20
    Activations Density 0.019%

    No Known Activations